microsoft/Phi-4-multimodal-instruct
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| WER | speech-asr | 99.63 | fleurs-ko2en-cot | fleurs-en2ko-cot | low | | original | 99.16 | 99.63 | 5.63 | 2.42 | 6.86 | 4.17 | |
| CER | speech-asr | 99.16 | fleurs-ko2en-cot | fleurs-en2ko-cot | low | | original | 99.16 | 99.63 | 5.63 | 2.42 | 6.86 | 4.17 | |
| DocVQA | multimodal | 93.2 | DocVQA | medium | | DocVQA | **93.2** | 69.3 | 93.9 | 91.6 | **95.7** | 93.0 | 91.2 | 92.1 | 95.2 | 90.9 | |
| DocVQA | multimodal | 87.3 | s_DocVQA | medium | | s_DocVQA | **87.3** | 79.9 | 76.0 | 80.3 | 78.2 | |
| MMBench | multimodal | 86.7 | MMBench (dev-en) | medium | | MMBench (dev-en) | **86.7** | 81.9 | 84.3 | 86.8 | 87.8 | 88.2 | 85.0 | **90.0** | 86.7 | 89.0 | |
| ChartQA | multimodal | 81.4 | ChartQA | medium | | ChartQA | **81.4** | 81.8 | 80.0 | 79.1 | **85.0** | 81.0 | 73.0 | 79.0 | 78.4 | 75.1 | |
| ChartQA | multimodal | 69.0 | s_ChartQA | medium | | s_ChartQA | **69.0** | 56.1 | 35.5 | 51.3 | 46.9 | |
| MathVista | multimodal | 62.4 | MathVista (testmini) | medium | | MathVista (testmini) | **62.4** | 43.9 | 60.8 | 51.2 | **67.8** | 56.7 | 57.6 | 47.2 | 56.9 | 56.1 | |
| MMMU | multimodal | 55.1 | MMMU | medium | | MMMU | **55.1** | 43.0 | 47.0 | 48.3 | 51.8 | 50.6 | 54.1 | **64.7** | 55.8 | 61.7 | |
| MMMU | multimodal | 38.5 | MMMU-Pro (std/vision) | medium | | MMMU-Pro (std/vision) | **38.5** | 21.8 | 29.9 | 32.4 | 36.9 | 34.4 | 45.1 | **54.4** | 54.3 | 53.0 | |
| WER | speech-asr | 6.14 | medium | word error rate 6.14% | |
| WER FLEURS | speech-asr | 5.63 | fleurs-ko2en-cot | fleurs-en2ko-cot | low | | original | 99.16 | 99.63 | 5.63 | 2.42 | 6.86 | 4.17 | |
none scraped.